scispace - formally typeset
Proceedings ArticleDOI

Real-time collision avoidance at road-crossings on board the Prometheus-ProLab 2 vehicle

Reads0
Chats0
TLDR
The control system presented in this paper is part of the European Prometheus-ProLab 2 test vehicle which proposes several new significant aids to the driver for an enhanced traffic safety.
Abstract
The control system presented in this paper is part of the European Prometheus-ProLab 2 test vehicle which proposes several new significant aids to the driver for an enhanced traffic safety. The goal of this system is to detect and to provide a low-level interpretation of the movements of side-obstacles (vehicles) occurring at crossings. The system is composed of two video cameras and a real-time vision machine (Transvision) on which a specific software performing the obstacle detection and interpretation task has been implemented. The proposed system provides reliable and robust (real-time) control of standard intersections up to a distance of about 150 m.

read more

Citations
More filters
Patent

Vision system for vehicle

TL;DR: In this article, a forward-facing vision system for a vehicle includes a forwardfacing camera disposed in a windshield electronics module attached at a windshield of the vehicle and viewing through the windshield.
Patent

Vehicular vision system

TL;DR: In this article, the camera is disposed at an interior portion of a vehicle equipped with the vehicular vision system, where the camera one of (i) views exterior of the equipped vehicle through the windshield of the vehicle and forward of the equipment and (ii) views from the windshield into the interior cabin of the equipments.
Patent

Driver assistance system for vehicle

TL;DR: In this paper, an adaptive speed control system for controlling the speed of a vehicle is proposed to detect a curve in the road ahead of the vehicle via processing by the image processor of image data captured by the imaging device.
Journal ArticleDOI

Real-time tracking of moving persons by exploiting spatio-temporal image slices

TL;DR: An original and efficient approach to track the apparent contours of a moving articulated structure, avoiding the use of 3D models is developed, which exploits spatio-temporal XT-slices from the image sequence volume XYT, where typical trajectory patterns can be associated with articulated motion such as human walking.
Patent

Vehicle vision system

TL;DR: In this article, the authors present a control to determine an object present in the first and/or second forward fields of view of a vehicle by processing image data captured by both of the imaging sensors.
References
More filters
Journal ArticleDOI

Multimodal estimation of discontinuous optical flow using Markov random fields

TL;DR: It is shown that multiple constraints can provide more accurate flow estimation in a wide range of circumstances and is presented a multimodal approach to the problem of motion estimation in which the computation of visual motion is based on several complementary constraints.
Proceedings ArticleDOI

A hierarchical statistical framework for the segmentation of deformable objects in image sequences

Kervrann, +1 more
TL;DR: A new statistical framework for modeling and extracting 2D moving deformable objects from image sequences that yields robust and reliable segmentations in adverse situations such as low signal-to-noise ratio, non-gaussian noise or occlusions is proposed.
Journal ArticleDOI

Recovery of moving object masks in an image sequence using local spatiotemporal contextual information

TL;DR: An original framework to solve this labeling problem is described, based on a statistical regularization approach using spatiotemporal Markov fields, that takes temporal variations of the intensity function as observations and delivers two-symbol label maps.
Proceedings ArticleDOI

Edge and region image segmentation processes on the parallel vision machine: Transvision

TL;DR: The authors define the most suitable target machine for helping with a real time application and present parallelization schemes and the temporal performances obtained for each of the chains.
Journal ArticleDOI

Efficient parallel nonlinear multigrid relaxation algorithms for low-level vision applications

TL;DR: This research note presents an algorithmic framework which enables the full use of the large potential of data parallelism for the implementation of nonlinear multigrid relaxation methods, and combines two different levels of parallelism: parallel updating of the image sites and concurrent explorations of the configuration space of the problem.